Bookmark and Share

Technical Articles

Calibration is a key step in the process of going from raw video data to metadata that can be analyzed for actionable insights.


As we design deep learning networks, how can we quickly prototype the complete algorithm to get a sense of timing and performance on GPUs?


In image procession systems, light is a major factor alongside camera, sensor, optics and software.

By effectively using all compute resources, along with leveraging software toolsets, it's possible to deliver robust AR in embedded designs.


This article showcases OpenVX implementations leveraging multiple hardware platforms and both traditional and deep learning algorithms.


This article focuses on recent updates to OpenVX, along with the set of extensions that OpenVX implementers can optionally provide.


The new CMOS technology has made NIR optimization affordable, through a line of industrial cameras with excellent sensitivity the NIR.

The robustness and reliability of a self-driving car’s computer vision system has received a lot of news coverage.

Real-time capability is especially relevant for applications where speed is crucial or when activity must be synchronized with other systems

Both CCD and CMOS sensors convert light to electrical signals. The sensors differ primarily in their underlying technological setup.